Sample Dropout for Audio Scene Classification Using Multi-Scale Dense Connected Convolutional Neural Network

TL;DR

This paper introduces a multi-scale DenseNet architecture combined with a novel sample dropout method to enhance audio scene classification accuracy and robustness, effectively handling outliers in training data.

Contribution

It proposes a multi-scale DenseNet model for improved feature extraction and a new sample dropout technique to reduce outliers, advancing audio scene classification methods.

Findings

Multi-scale DenseNet outperforms single-scale DenseNet.

Sample dropout improves model robustness.

The approach achieves superior accuracy on DCASE 2017 dataset.

Abstract

Acoustic scene classification is an intricate problem for a machine. As an emerging field of research, deep Convolutional Neural Networks (CNN) achieve convincing results. In this paper, we explore the use of multi-scale Dense connected convolutional neural network (DenseNet) for the classification task, with the goal to improve the classification performance as multi-scale features can be extracted from the time-frequency representation of the audio signal. On the other hand, most of previous CNN-based audio scene classification approaches aim to improve the classification accuracy, by employing different regularization techniques, such as the dropout of hidden units and data augmentation, to reduce overfitting. It is widely known that outliers in the training set have a high negative influence on the trained model, and culling the outliers may improve the classification performance, while it is often under-explored in previous studies. In this paper, inspired by the silence removal in the speech signal processing, a novel sample dropout approach is proposed, which aims to remove outliers in the training dataset. Using the DCASE 2017 audio scene classification datasets, the experimental results demonstrates the proposed multi-scale DenseNet providing a superior performance than the traditional single-scale DenseNet, while the sample dropout method can further improve the classification robustness of multi-scale DenseNet.